AAAI-MLPS 2021
AAAI 2021 Spring Symposium on
Combining Artificial Intelligence and Machine Learning with Physics Sciences
March 22-24, 2021 9 AM - 5 PM Pacific Time with video conferencing
Stanford University, Palo Alto, California, USA
AAAI 2021 Spring Symposium on
Combining Artificial Intelligence and Machine Learning with Physics Sciences
March 22-24, 2021 9 AM - 5 PM Pacific Time with video conferencing
Stanford University, Palo Alto, California, USA
Register for the symposium using the link below!
With recent advances in scientific data acquisition and high-performance computing, Artificial Intelligence (AI) and Machine Learning (ML) have received significant attention from the applied mathematics and physics science community. Complementing successes reported by industry, academia, and research communities, we observe that AI and ML have great potential to leverage scientific domain knowledge to support new scientific discoveries and enhance the development of physical models and scientific understanding for complex natural and engineering systems.
For example, deep learning supports discovery of new materials and high-energy physics from numerous computer simulations and experiments and lets us learn low-dimensional manifolds underlying the acquired data in order to represent the system of interest parsimoniously and effectively. ML has offered new insights on adaptive numerical discretization schemes and numerical solvers, which are clearly distinct from traditional mathematical theories. AI also provides a new way of generalizing constitutive physics laws based on big scientific data sets.
Despite the progress, there are still many open questions. Our current understanding is limited regarding how and why AI/ML work and why they can be predictive. AI has been shown to outperform traditional methods in many cases especially with high-dimensional, inhomogeneous data sets. However, a rigorous understanding of when AI/ML is the right approach is largely lacking: for what class of problems, underlying assumptions, available data sets, and constraints are these new methods best suited? The lack of interpretability in AI-based modeling and related scientific theories makes them insufficient for high-impact, safety-critical applications such as medical diagnoses, national security, and environmental contamination.
With transparency and a clear understanding of the data-driven mechanism, desirable properties of AI should be best utilized to extend current methods in physical and engineering modeling. Handling expensive training costs and large memory requirements for ever-increasing scientific data sets becomes also important to guarantee scalable science machine learning. In addition, methods from the physical sciences and scientific community hold the promise for a more scientific approach to ML in the physical sciences, for instance, adaptive and second-order methods that can provide efficient and more robust algorithms for training; theory for the choice of initialization, which is essential for robustness and good generalization especially when labelled data are expensive; and mathematical optimization for DNN structure/architecture identification which is still largely based on the trial and error.
This symposium will aim to present the current state of the art and identify opportunities and gaps in AI/ML-based physics science. The symposium will focus on challenges and opportunities for increasing the scale, rigor, robustness, and reliability of physics-informed AI necessary for routine use in science and engineering applications and discuss potential researcher-AI collaborations to significantly advance diverse scientific areas and transform the way science is done.
Authors are strongly encouraged to present papers that combine and blend physical knowledge and artificial intelligence/machine learning algorithms. Topics of interest include but are not limited to the following:
Artificial intelligence/machine learning framework that can seamlessly synthesize models, governing equations and data,
Approaches to encode scientific knowledge in machine learning method and architecture,
Architectural and algorithmic improvements for scalable physics-informed learning,
Stability and error analysis for physics-informed learning,
Software development facilitating the inclusion of physics domain knowledge in learning,
Discovery of physically interpretable laws from data,
Applications incorporating domain knowledge into machine learning
3/20/2021: Accepted papers are now available in Proceedings.
3/16/2021: Zoom link sent to registered participants. Please let us know if you have not received the zoom link.
3/9/2021: Symposium schedule posted.
2/11/2021: Registration is now available. Additional information can be found at the AAAI Spring Symposium website.
11/17/2020: The submission deadline has been extended to December 7, 2020
10/30/2020: Our symposium has been converted to virtual meeting
9/9/2020: Our symposium CFP has been published.
8/13/2020: Our symposium proposal has been accepted.
Abstract/paper submission due: December 7, 2020 11:59 PM PT
Notification of authors: Feb 19, 2021
Registration open: Feb 11, 2021
Registration for invited participants: Feb 26, 2021
Registration deadline: March 5, 2021
Symposium: March 22-24, 2021